• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on artificial neural networks >Continual Learning Exploiting Structure of Fractal Reservoir Computing
【24h】

Continual Learning Exploiting Structure of Fractal Reservoir Computing

机译：分形储层计算的持续学习开发结构

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Neural network has a critical problem, called catastrophic forgetting, where memories for tasks already learned are easily overwritten with memories for a task additionally learned. This problem interferes with continual learning required for autonomous robots, which learn many tasks incrementally from daily activities. To mitigate the catastrophic forgetting, it is important for especially reservoir computing to clarify which neurons should be fired corresponding to each task, since only readout weights are updated according to the degree of firing of neurons. We therefore propose the way to design reservoir computing such that the firing neurons are clearly distinguished from others according to the task to be performed. As a key design feature, we employ fractal network, which has modularity and scalability, to be reservoir layer. In particular, its modularity is fully utilized by designing input layer. As a result, simulations of control tasks using reinforcement learning show that our design mitigates the catastrophic forgetting even when random actions from reinforcement learning prompt parameters to be overwritten. Furthermore, learning multiple tasks with a single network suggests that knowledge for the other tasks can facilitate to learn a new task, unlike the case using completely different networks.
机译：神经网络有一个严重的问题，称为灾难性遗忘，其中已经学习的任务的记忆很容易被另外学习的任务的记忆覆盖。此问题会干扰自主机器人所需的持续学习，后者会从日常活动中逐步学习许多任务。为了减轻灾难性的遗忘，特别重要的是，对于储层计算，应明确应对应于每个任务触发哪些神经元，因为只有读出权重会根据神经元的触发程度进行更新。因此，我们提出了一种设计储层计算的方法，以便根据要执行的任务将发射神经元与其他神经元区分开。作为关键设计特征，我们采用具有模块化和可扩展性的分形网络作为储层。特别是，通过设计输入层可以充分利用其模块化。结果，使用强化学习对控制任务进行的仿真表明，即使来自强化学习的随机动作提示参数被覆盖，我们的设计也可以减轻灾难性的遗忘。此外，与使用完全不同的网络的情况不同，使用单个网络学习多个任务表明，其他任务的知识可以促进学习新任务。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号